added generate questions function with gemma, huggging face client

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 from utils import (
     evaluate_resumes, generate_pdf_report, store_in_supabase, extract_email,
-    score_candidate, parse_resume, summarize_resume, extract_keywords
+    score_candidate, parse_resume, summarize_resume, extract_keywords, generate_interview_questions_from_summaries
 )
 from config import supabase
 from config import HF_API_TOKEN, HF_HEADERS, HF_MODELS
@@ -52,6 +52,12 @@ def main():
             # Generate PDF Report
             pdf_report = generate_pdf_report(shortlisted)
             st.download_button("Download Shortlist Report", pdf_report, "shortlist.pdf")
+            
+            # Generate Interview Questions
+            questions = generate_interview_questions_from_summaries(shortlisted)
+            st.subheader("🧠 Suggested Interview Questions:")
+            for idx, q in enumerate(questions, 1):
+                st.markdown(f"**Q{idx}.** {q}")
 
         # 🔻 Display removed candidates due to missing keywords
         if removed_candidates:

config.py

@@ -19,7 +19,9 @@ supabase = create_client(SUPABASE_URL, SUPABASE_KEY)
 embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
 
 HF_MODELS = {
-    "bart": "https://router.huggingface.co/hf-inference/models/facebook/bart-large-cnn"
+    "bart": "https://router.huggingface.co/hf-inference/models/facebook/bart-large-cnn",
+    "gemma": "https://router.huggingface.co/nebius/v1/chat/completions"  
+
 }
 
 HF_API_TOKEN = os.getenv("HF_API_TOKEN")

utils.py

@@ -15,6 +15,15 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 import streamlit as st
 from fuzzywuzzy import fuzz
 import subprocess
+import random
+from huggingface_hub import InferenceClient
+import os
+
+# Initialize the client
+client = InferenceClient(
+    model="google/gemma-1.1-7b-it",
+    token=HF_API_TOKEN
+)
 
 # These functions will be called in the app.py file
 
@@ -28,7 +37,7 @@ except OSError:
 def evaluate_resumes(uploaded_files, job_description, min_keyword_match=2):
     """Evaluates uploaded resumes, filters by keywords and score, and returns shortlisted candidates."""
     candidates = []
-    removed_candidates = [] 
+    removed_candidates = []
 
     for pdf_file in uploaded_files:
         resume_text = parse_resume(pdf_file)
@@ -36,7 +45,6 @@ def evaluate_resumes(uploaded_files, job_description, min_keyword_match=2):
         email = extract_email(resume_text)
         summary = summarize_resume(resume_text)
 
-        # If score is below 0.20, remove the candidate immediately
         if score < 0.20:
             removed_candidates.append({"name": pdf_file.name, "reason": "Low confidence score (< 0.20)"})
             continue  # Skip adding to candidates list
@@ -49,14 +57,22 @@ def evaluate_resumes(uploaded_files, job_description, min_keyword_match=2):
             "summary": summary
         })
 
-    # Filter resumes based on job description keywords
-    filtered_candidates, keyword_removed = filter_resumes_by_keywords(candidates, job_description, min_keyword_match=2)
+    # 🔹 Step 2: Filter candidates based on keyword matches
+    filtered_candidates, keyword_removed = filter_resumes_by_keywords(candidates, job_description, min_keyword_match)
 
-    # Store removed candidates with a reason
+    # 🔹 Step 3: Log removed candidates
     for name in keyword_removed:
         removed_candidates.append({"name": name, "reason": "Insufficient keyword matches"})
 
-    return sorted(filtered_candidates, key=lambda x: x["score"], reverse=True)[:5], removed_candidates
+    # 🔹 Step 4: Ensure the final list is sorted by score and limit to top 5 candidates
+    shortlisted_candidates = sorted(filtered_candidates, key=lambda x: x["score"], reverse=True)[:5]
+
+    # 🔹 Step 5: Ensure return value is always a list
+    if not isinstance(shortlisted_candidates, list):
+        print("⚠️ ERROR: shortlisted_candidates is not a list! Returning empty list.")
+        return [], removed_candidates
+
+    return shortlisted_candidates, removed_candidates
 
 def extract_keywords(text, top_n=10):
     """Extracts key terms from the job description using TF-IDF and spaCy."""
@@ -212,6 +228,10 @@ def generate_pdf_report(shortlisted_candidates):
 
         # Use stored summary, or provide a fallback
         summary = candidate.get("summary", "No summary available")
+        
+        # Generate interview questions
+        #questions = generate_interview_questions_from_summaries(summary)
+        #questions_text = "\n".join([f"- {q}" for q in questions])
 
         # Define text area properties
         text_box_x = 50  # Left margin
@@ -226,6 +246,7 @@ def generate_pdf_report(shortlisted_candidates):
             f"Email: {candidate['email']}\n"
             f"Score: {candidate['score']}\n\n"
             f"Summary:\n{summary}"
+            #f"Suggested Interview Questions:\n{questions_text}"
         )
 
         # Check if the text fits in the allowed area
@@ -240,4 +261,36 @@ def generate_pdf_report(shortlisted_candidates):
 
     doc.save(pdf)
     pdf.seek(0)
-    return pdf
+    return pdf
+
+def generate_interview_questions_from_summaries(candidates):
+    """
+    Generates common interview questions based on the combined summaries of shortlisted candidates.
+    Uses the Hugging Face Gemma model to generate questions.
+    """
+    if not isinstance(candidates, list):
+        raise TypeError("Expected a list of candidate dictionaries.")
+
+    summaries = [c.get("summary", "") for c in candidates if "summary" in c]
+    combined_summary = " ".join(summaries)
+
+    prompt = (
+        "Based on the following summary of this top candidate for a job role, generate 5 thoughtful, general interview questions that would help a recruiter assess their fit:\n"
+        f"{combined_summary}"
+    )
+
+    try:
+        response = client.chat_completion(
+            messages=[
+                {"role": "user", "content": prompt}
+            ],
+            temperature=0.7,
+            max_tokens=500
+        )
+        result_text = response.choices[0].message.content
+        questions = [q.strip() for q in result_text.split("\n") if q.strip()]
+        return questions[:5] if questions else ["⚠️ No questions generated."]
+    except Exception as e:
+        print(f"❌ Error generating interview questions: {e}")
+        return ["⚠️ Error generating questions."]
+